Toward Machines that Improve with Experience
March 20, 2017 | DARPAEstimated reading time: 3 minutes
Self-driving taxis. Cell phones that react appropriately to spoken requests. Computers that outcompete world-class chess and Go players. Artificial Intelligence (AI) is becoming part and parcel of the technological landscape—not only in the civilian and commercial worlds but also within the Defense Department, where AI is finding application in such arenas as cybersecurity and dynamic logistics planning.
But even the smartest of the current crop of AI systems can’t stack up against adaptive biological intelligence. These high-profile examples of AI all rely on clever programming and extensive training datasets—a framework referred to as Machine Learning (ML)—to accomplish seemingly intelligent tasks. Unless their programming or training sets have specifically accounted for a particular element, situation, or circumstance, these ML systems are stymied, unable to determine what to do.
That’s a far cry from what even simple biological systems can do as they adapt to and learn from experience. And it’s light years short of how, say, human motorists build on experience as they encounter the dynamic vagaries of real-world driving—becoming ever more adept at handling never-before-encountered challenges on the road.
This is where DARPA’s new Lifelong Learning Machines (L2M) program comes in.
The technical goal of L2M is to develop next-generation ML technologies that can learn from new situations and apply that learning to become better and more reliable, while remaining constrained within a predetermined set of limits that the system cannot override. Such a capability for automatic and ongoing learning could, for example, help driverless vehicles become safer as they apply knowledge gained from previous experiences—including the accidents, blind spots, and vulnerabilities they encounter on roadways—to circumstances they weren’t specifically programmed or trained for.
“Life is by definition unpredictable. It is impossible for programmers to anticipate every problematic or surprising situation that might arise, which means existing ML systems remain susceptible to failures as they encounter the irregularities and unpredictability of real-world circumstances,” said L2M program manager Hava Siegelmann. “Today, if you want to extend an ML system’s ability to perform in a new kind of situation, you have to take the system out of service and retrain it with additional data sets relevant to that new situation. This approach is just not scalable.”
To get there, the L2M program aims to develop fundamentally new ML mechanisms that will enable systems to learn from experience on the fly—much the way children and other biological systems do, using life as a training set. The basic understanding of how to develop a machine that could truly improve from experience by gaining generalizable lessons from specific situations is still immature. The L2M program will provide a unique opportunity to build a community of computer scientists and biologists to explore these new mechanisms.
“Enabling a computer to learn even the simplest things from experience has been a longstanding but elusive goal,” said Siegelmann. “That’s because today’s computers are designed to run on prewritten programs incapable of adapting as they execute, a model that hasn’t changed since the British polymath Alan Turing developed the earliest computing machines in the 1930s. L2M calls for a new computing paradigm.”
The four-year L2M program features two technical areas. The first aims to develop ML frameworks that can continuously apply the results of past experience and adapt “lessons learned” to new data or situations. Simultaneously, it calls for the development of techniques for monitoring an ML system’s behavior, setting limits on the scope of its ability to adapt, and intervening in the system’s functions as needed. The research will encompass network theory, algorithms, software, and computer architectures. The second technical area, which derives from Siegelmann’s longstanding interest in biological learning mechanisms, will focus specifically on how living systems learn and adapt and will consider whether and how those principles and techniques can be applied to ML systems. “Life has had billions of years to develop approaches for learning from experience,” Siegelmann said. “There are almost certainly some secrets there that can be applied to machines so they can be not just computational tools to help us solve problems but responsive and adaptive collaborators.”
Suggested Items
Real Time with... IPC APEX EXPO 2024: AI Implementation at Omron
04/18/2024 | Real Time with...IPC APEX EXPOEditor Nolan Johnson and Omron Product Manager Nick Fieldhouse discuss the company's focus on AI implementation to enhance customer experience and results. They address programming challenges and how AI can help customers achieve better outcomes with less experience. Omron's AI is compatible with existing systems, facilitating easy upgrades.
Cadence Unveils Palladium Z3 and Protium X3 Systems
04/18/2024 | Cadence Design SystemsThe Palladium Z3 and Protium X3 systems offer increased capacity, and scale from job sizes of 16 million gates up to 48 billion gates, so the largest SoCs can be tested as a whole rather than just partial models, ensuring proper functionality and performance.
Australian Flow Batteries and The SCHMID Group Announce Groundbreaking Memorandum of Understanding
04/17/2024 | SCHMID GroupAustralian Flow Batteries Pty Ltd (AFB), a leader in innovative energy solutions and economical, safe, and reliable power storage, and SCHMID Energy Systems GmbH a company of the German SCHMID Group, a global technology leader with a rich history in delivering innovative solutions across multiple industries including Electronics, Renewables, and Energy Storage sectors, are thrilled to announce the signing of a Memorandum of Understanding (MoU)
Ansys Joins BAE Systems’ Mission Advantage Program to Advance Digital Engineering Across US Department of Defense
04/16/2024 | ANSYSAnsys announced it is working with BAE Systems, Inc., to accelerate the adoption of digital engineering and MBSE across the Department of Defense (DoD).
Designing Electronics for High Thermal Loads
04/16/2024 | Akber Roy, Rush PCB Inc.Developing proactive thermal management strategies is important in the early stages of the PCB design cycle to minimize costly redesign iterations. Here, I delve into key aspects of electronic design that hold particular relevance for managing heat in electronic systems. Each of these considerations plays a pivotal role in enhancing the reliability and performance of the overall system.